# jtydhr88/screenwriting-skills > A set of 24 agent skills (SKILL.md, agentskills.io standard) for Claude Code and OpenAI Codex covering screenwriting, TV writing and dramaturgy, distilled from 45 craft books and 23 volumes of scripts and plays. - Magnitude: 1.6 out of 10 — Steady - Stars: 1,677 total · +12 stars measured 2026-10-15, 00:28–23:29 UTC - Star trust: star growth looks organic - Category: AI agents · Language: Python · License: MIT · Created: 2026-09-06 · Last push: 2026-10-03 - GitHub: https://github.com/jtydhr88/screenwriting-skills · Page: https://gitnova.dev/en/r/jtydhr88/screenwriting-skills ## Useful for - Break a 12-episode series into acts and place the act outs - Rewrite an on-the-nose dialogue scene using sw-dialogue and sw-scene-craft - Turn a 400,000-word novel into a 40-episode Chinese drama outline ## Why it’s here - Star-counter measurements on 2026-10-15 (UTC), 00:28–23:29: 1665 → 1677 stars (+12). This is the change over that interval. - The repository is 39 days old and already has 1,677 stars. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 176 - Issues and pull requests: 27 - Watchers: 7 - Average over the last week: 11 per day - Usual pace: 22 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-09-30 … 2026-10-29: 8, 56, 16, 11, 12, 9, 10, 14, 15, 11, 6, 9, 10, 11, 15, 7, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 10-02 2.3, 10-03 1.5, 10-04 1.4, 10-05 1.5, 10-06 1.5, 10-07 1.4, 10-08 1.7, 10-09 1.8, 10-10 1.3, 10-11 1.2, 10-12 1.3, 10-13 1.4, 10-14 1.5, 10-15 1.6 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-15 23:34 UTC, updated every 30 minutes.